Recognition of Maize Phenology in Sentinel Images with Machine Learning

The scarcity of water for agricultural use is a serious problem that has increased due to intense droughts, poor management, and deficiencies in the distribution and application of the resource. The monitoring of crops through satellite image processing and the application of machine learning algorithms are technological strategies with which developed countries tend to implement better public policies regarding the efficient use of water. The purpose of this research was to determine the main indicators and characteristics that allow us to discriminate the phenological stages of maize crops (Zea mays L.) in Sentinel 2 satellite images through supervised classification models. The training data were obtained by monitoring cultivated plots during an agricultural cycle. Indicators and characteristics were extracted from 41 Sentinel 2 images acquired during the monitoring dates. With these images, indicators of texture, vegetation, and colour were calculated to train three supervised classifiers: linear discriminant (LD), support vector machine (SVM), and k-nearest neighbours (kNN) models. It was found that 45 of the 86 characteristics extracted contributed to maximizing the accuracy by stage of development and the overall accuracy of the trained classification models. The characteristics of the Moran’s I local indicator of spatial association (LISA) improved the accuracy of the classifiers when applied to the L*a*b* colour model and to the near-infrared (NIR) band. The local binary pattern (LBP) increased the accuracy of the classification when applied to the red, green, blue (RGB) and NIR bands. The colour ratios, leaf area index (LAI), RGB colour model, L*a*b* colour space, LISA, and LBP extracted the most important intrinsic characteristics of maize crops with regard to classifying the phenological stages of the maize cultivation. The quadratic SVM model was the best classifier of maize crop phenology, with an overall accuracy of 82.3%.

Download Full-text

Delineating Smallholder Maize Farms from Sentinel-1 Coupled with Sentinel-2 Data Using Machine Learning

Sustainability ◽

10.3390/su13094728 ◽

2021 ◽

Vol 13 (9) ◽

pp. 4728

Author(s):

Zinhle Mashaba-Munghemezulu ◽

George Johannes Chirima ◽

Cilence Munghemezulu

Keyword(s):

Machine Learning ◽

Food Security ◽

Rural Communities ◽

Machine Learning Algorithms ◽

Support Vector ◽

Subsistence Agriculture ◽

Smallholder Farms ◽

Main Driver ◽

Sentinel 2

Rural communities rely on smallholder maize farms for subsistence agriculture, the main driver of local economic activity and food security. However, their planted area estimates are unknown in most developing countries. This study explores the use of Sentinel-1 and Sentinel-2 data to map smallholder maize farms. The random forest (RF), support vector (SVM) machine learning algorithms and model stacking (ST) were applied. Results show that the classification of combined Sentinel-1 and Sentinel-2 data improved the RF, SVM and ST algorithms by 24.2%, 8.7%, and 9.1%, respectively, compared to the classification of Sentinel-1 data individually. Similarities in the estimated areas (7001.35 ± 1.2 ha for RF, 7926.03 ± 0.7 ha for SVM and 7099.59 ± 0.8 ha for ST) show that machine learning can estimate smallholder maize areas with high accuracies. The study concludes that the single-date Sentinel-1 data were insufficient to map smallholder maize farms. However, single-date Sentinel-1 combined with Sentinel-2 data were sufficient in mapping smallholder farms. These results can be used to support the generation and validation of national crop statistics, thus contributing to food security.

Download Full-text

A Machine Learning Approach for Mapping Forest Vegetation in Riparian Zones in an Atlantic Biome Environment Using Sentinel-2 Imagery

Remote Sensing ◽

10.3390/rs12244086 ◽

2020 ◽

Vol 12 (24) ◽

pp. 4086

Author(s):

Danielle Elis Garcia Furuya ◽

João Alex Floriano Aguiar ◽

Nayara V. Estrabis ◽

Mayara Maezano Faita Pinheiro ◽

Michelle Taís Garcia Furuya ◽

...

Keyword(s):

Machine Learning ◽

Environmental Planning ◽

Riparian Zone ◽

Learning Algorithms ◽

Vegetation Mapping ◽

Forest Vegetation ◽

Machine Learning Algorithms ◽

Riparian Zones ◽

Support Vector ◽

Sentinel 2

Riparian zones consist of important environmental regions, specifically to maintain the quality of water resources. Accurately mapping forest vegetation in riparian zones is an important issue, since it may provide information about numerous surface processes that occur in these areas. Recently, machine learning algorithms have gained attention as an innovative approach to extract information from remote sensing imagery, including to support the mapping task of vegetation areas. Nonetheless, studies related to machine learning application for forest vegetation mapping in the riparian zones exclusively is still limited. Therefore, this paper presents a framework for forest vegetation mapping in riparian zones based on machine learning models using orbital multispectral images. A total of 14 Sentinel-2 images registered throughout the year, covering a large riparian zone of a portion of a wide river in the Pontal do Paranapanema region, São Paulo state, Brazil, was adopted as the dataset. This area is mainly composed of the Atlantic Biome vegetation, and it is near to the last primary fragment of its biome, being an important region from the environmental planning point of view. We compared the performance of multiple machine learning algorithms like decision tree (DT), random forest (RF), support vector machine (SVM), and normal Bayes (NB). We evaluated different dates and locations with all models. Our results demonstrated that the DT learner has, overall, the highest accuracy in this task. The DT algorithm also showed high accuracy when applied on different dates and in the riparian zone of another river. We conclude that the proposed approach is appropriated to accurately map forest vegetation in riparian zones, including temporal context.

Download Full-text

A Comparison of Hybrid Machine Learning Algorithms for the Retrieval of Wheat Biophysical Variables from Sentinel-2

Remote Sensing ◽

10.3390/rs11050481 ◽

2019 ◽

Vol 11 (5) ◽

pp. 481 ◽

Cited By ~ 26

Author(s):

Deepak Upreti ◽

Wenjiang Huang ◽

Weiping Kong ◽

Simone Pascucci ◽

Stefano Pignatti ◽

...

Keyword(s):

Machine Learning ◽

Least Squares ◽

Chlorophyll Content ◽

Learning Algorithms ◽

Machine Learning Algorithms ◽

Area Index ◽

Random Forest Tree ◽

Ground Validation ◽

Study Sites ◽

Sentinel 2

This study focuses on the comparison of hybrid methods of estimation of biophysical variables such as leaf area index (LAI), leaf chlorophyll content (LCC), fraction of absorbed photosynthetically active radiation (FAPAR), fraction of vegetation cover (FVC), and canopy chlorophyll content (CCC) from Sentinel-2 satellite data. Different machine learning algorithms were trained with simulated spectra generated by the physically-based radiative transfer model PROSAIL and subsequently applied to Sentinel-2 reflectance spectra. The algorithms were assessed against a standard operational approach, i.e., the European Space Agency (ESA) Sentinel Application Platform (SNAP) toolbox, based on neural networks. Since kernel-based algorithms have a heavy computational cost when trained with large datasets, an active learning (AL) strategy was explored to try to alleviate this issue. Validation was carried out using ground data from two study sites: one in Shunyi (China) and the other in Maccarese (Italy). In general, the performance of the algorithms was consistent for the two study sites, though a different level of accuracy was found between the two sites, possibly due to slightly different ground sampling protocols and the range and variability of the values of the biophysical variables in the two ground datasets. For LAI estimation, the best ground validation results were obtained for both sites using least squares linear regression (LSLR) and partial least squares regression, with the best performances values of R2 of 0.78, rott mean squared error (RMSE) of 0.68 m2 m−2 and a relative RMSE (RRMSE) of 19.48% obtained in the Maccarese site with LSLR. The best results for LCC were obtained using Random Forest Tree Bagger (RFTB) and Bagging Trees (BagT) with the best performances obtained in Maccarese using RFTB (R2 = 0.26, RMSE = 8.88 μg cm−2, RRMSE = 17.43%). Gaussian Process Regression (GPR) was the best algorithm for all variables only in the cross-validation phase, but not in the ground validation, where it ranked as the best only for FVC in Maccarese (R2 = 0.90, RMSE = 0.08, RRMSE = 9.86%). It was found that the AL strategy was more efficient than the random selection of samples for training the GPR algorithm.

Download Full-text

A COMPARISON OF MACHINE-LEARNING REGRESSION ALGORITHMS FOR THE ESTIMATION OF LAI USING LANDSAT - 8 SATELLITE DATA

ISPRS - International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences ◽

10.5194/isprs-archives-xlii-4-w16-679-2019 ◽

2019 ◽

Vol XLII-4/W16 ◽

pp. 679-683

Author(s):

V. P. Yadav ◽

R. Prasad ◽

R. Bala ◽

A. K. Vishwakarma ◽

S. A. Yadav ◽

...

Keyword(s):

Machine Learning ◽

Satellite Data ◽

Vegetation Index ◽

Learning Algorithms ◽

Machine Learning Algorithms ◽

Accurate Estimation ◽

Support Vector ◽

Landsat 8 ◽

Area Index ◽

Global Circulation Models

Abstract. The leaf area index (LAI) is one of key variable of crops which plays important role in agriculture, ecology and climate change for global circulation models to compute energy and water fluxes. In the recent research era, the machine-learning algorithms have provided accurate computational approaches for the estimation of crops biophysical parameters using remotely sensed data. The three machine-learning algorithms, random forest regression (RFR), support vector regression (SVR) and artificial neural network regression (ANNR) were used to estimate the LAI for crops in the present study. The three different dates of Landsat-8 satellite images were used during January 2017 – March 2017 at different crops growth conditions in Varanasi district, India. The sampling regions were fully covered by major Rabi season crops like wheat, barley and mustard etc. In total pooled data, 60% samples were taken for the training of the algorithms and rest 40% samples were taken as testing and validation of the machinelearning regressions algorithms. The highest sensitivity of normalized difference vegetation index (NDVI) with LAI was found using RFR algorithms (R2 = 0.884, RMSE = 0.404) as compared to SVR (R2 = 0.847, RMSE = 0.478) and ANNR (R2 = 0.829, RMSE = 0.404). Therefore, RFR algorithms can be used for accurate estimation of LAI for crops using satellite data.

Download Full-text

FEASIBILITY OF MACHINE LEARNING METHODS FOR SEPARATING WOOD AND LEAF POINTS FROM TERRESTRIAL LASER SCANNING DATA

ISPRS Annals of Photogrammetry Remote Sensing and Spatial Information Sciences ◽

10.5194/isprs-annals-iv-2-w4-157-2017 ◽

2017 ◽

Vol IV-2/W4 ◽

pp. 157-164 ◽

Cited By ~ 6

Author(s):

D. Wang ◽

M. Hollaus ◽

N. Pfeifer

Keyword(s):

Machine Learning ◽

Laser Scanning ◽

Learning Algorithms ◽

Terrestrial Laser Scanning ◽

Gaussian Mixture ◽

Machine Learning Algorithms ◽

Support Vector ◽

Area Index ◽

Training Samples

Classification of wood and leaf components of trees is an essential prerequisite for deriving vital tree attributes, such as wood mass, leaf area index (LAI) and woody-to-total area. Laser scanning emerges to be a promising solution for such a request. Intensity based approaches are widely proposed, as different components of a tree can feature discriminatory optical properties at the operating wavelengths of a sensor system. For geometry based methods, machine learning algorithms are often used to separate wood and leaf points, by providing proper training samples. However, it remains unclear how the chosen machine learning classifier and features used would influence classification results. To this purpose, we compare four popular machine learning classifiers, namely Support Vector Machine (SVM), Na¨ıve Bayes (NB), Random Forest (RF), and Gaussian Mixture Model (GMM), for separating wood and leaf points from terrestrial laser scanning (TLS) data. Two trees, an <i>Erytrophleum fordii</i> and a <i>Betula pendula</i> (silver birch) are used to test the impacts from classifier, feature set, and training samples. Our results showed that RF is the best model in terms of accuracy, and local density related features are important. Experimental results confirmed the feasibility of machine learning algorithms for the reliable classification of wood and leaf points. It is also noted that our studies are based on isolated trees. Further tests should be performed on more tree species and data from more complex environments.

Download Full-text

Prediction of higher-selectivity catalysts by computer-driven workflow and machine learning

Science ◽

10.1126/science.aau5631 ◽

2019 ◽

Vol 363 (6424) ◽

pp. eaau5631 ◽

Cited By ~ 66

Author(s):

Andrew F. Zahrt ◽

Jeremy J. Henle ◽

Brennan T. Rose ◽

Yang Wang ◽

William T. Darrow ◽

...

Keyword(s):

Machine Learning ◽

Catalyst Design ◽

Machine Learning Algorithms ◽

Support Vector ◽

Asymmetric Reaction ◽

Stage Of Development ◽

Chiral Phosphoric Acid ◽

Vector Machines ◽

Feed Forward Neural Networks ◽

Selection Of

Catalyst design in asymmetric reaction development has traditionally been driven by empiricism, wherein experimentalists attempt to qualitatively recognize structural patterns to improve selectivity. Machine learning algorithms and chemoinformatics can potentially accelerate this process by recognizing otherwise inscrutable patterns in large datasets. Herein we report a computationally guided workflow for chiral catalyst selection using chemoinformatics at every stage of development. Robust molecular descriptors that are agnostic to the catalyst scaffold allow for selection of a universal training set on the basis of steric and electronic properties. This set can be used to train machine learning methods to make highly accurate predictive models over a broad range of selectivity space. Using support vector machines and deep feed-forward neural networks, we demonstrate accurate predictive modeling in the chiral phosphoric acid–catalyzed thiol addition toN-acylimines.

Download Full-text

MULTI-SENSOR APPROACH TO LEAF AREA INDEX ESTIMATION USING STATISTICAL MACHINE LEARNING MODELS: A CASE ON MANGROVE FORESTS

ISPRS Annals of Photogrammetry Remote Sensing and Spatial Information Sciences ◽

10.5194/isprs-annals-v-3-2021-109-2021 ◽

2021 ◽

Vol V-3-2021 ◽

pp. 109-115

Author(s):

K. P. Martinez ◽

D. F. M. Burgos ◽

A. C. Blanco ◽

S. G. Salmo III

Keyword(s):

Machine Learning ◽

Leaf Area Index ◽

Leaf Area ◽

Machine Learning Algorithms ◽

Optical Parameters ◽

Mangrove Forests ◽

Sar Images ◽

Area Index ◽

Optical Images ◽

Sentinel 2

Abstract. Leaf Area Index (LAI) is a quantity that characterizes canopy foliage content. As leaf surfaces are the primary sites of energy, mass exchange, and fundamental production of terrestrial ecosystem, many important processes are directly proportional to LAI. With this, LAI can be considered as an important parameter of plant growth. Multispectral optical images have been widely utilized for mangrove-related studies, such as LAI estimation. In Sentinel-2, for example, LAI can be estimated using a biophysical processor in SNAP or using various machine learning algorithms. However, multispectral optical images have disadvantages due to its weather-dependence and limited canopy penetration. In this study, a multi-sensor approach was implemented by using free multi-spectral optical images (Sentinel-2 ) and synthetic aperture radar (SAR) images (Sentinel-1) to perform Leaf Area Index (LAI) estimation. The use of SAR images can compensate for the above-mentioned disadvantages and it then can pave the way for regular mapping and assessment of LAI, despite any weather conditions and cloud cover. In this study, generation of LAI models that explores linear, non-linear and decision trees modelling algorithms to incorporate Sentinel-1 derivatives and Sentinel-2 LAI were executed. The Random Forest model have exhibited the most robust model having the lowest RMSE of 0.2845. This result poses a concrete relationship of a biophysical entity derived from optical parameters to RADAR derivatives to which opens the opportunity of integrating both systems to compensate each disadvantages and produce a more efficient quantification of LAI.

Download Full-text

Machine Learning Based Classification Models for Diagnosis of Diabetes

Recent Advances in Computer Science and Communications ◽

10.2174/2666255814666210201103252 ◽

2021 ◽

Vol 14 ◽

Author(s):

Sushma Jaiswal ◽

Tarun Jaiswal

Keyword(s):

Machine Learning ◽

Type 2 Diabetes ◽

Support Vector Machine ◽

Expert System ◽

Learning Algorithms ◽

Machine Learning Algorithms ◽

Support Vector ◽

Fuzzy Expert System ◽

Classification Models

Introduction: The expansion of an actual diabetes judgement structure by the fascinating improvement of computational intellect is observed as a chief objective currently. Numerous tactics based on the artificial network and machine-learning procedures have been established and verified alongside diabetes datasets, which remained typically associated with the entities of Pima Indian derivation. Nevertheless, extraordinary accuracy up to 99-100% in forecasting the precise diabetes judgement, none of these methods has touched scientific presentation so far. Various tools such as Machine Learning (ML) and Data Mining are used for correct identification of diabetes. These tools improve the diagnosis process associated with T2DM. Diabetes mellitus type 2 (DMT2) is a major problem in several developing countries but its early diagnosis can provide enhanced treatment and can save several people life. Accordingly, we have to develop a structure that diagnoses type 2 diabetes. In this paper, a fuzzy expert system is proposed that present the Mamdani fuzzy inference structure (MFIS) to diagnose type 2 diabetes meritoriously. For necessary evaluation of the proposed structure, a proportional revision has been originated, that provide the anticipated structure with Machine Learning algorithms, specifically J48 Decision-tree (DT), multilayer perceptron (MLP), support-vector-machine (SVM), and Naïve- Bayes (NB), fusion and mixed fusion-based methods. The advanced fuzzy expert system (FES) and the machine learning algorithms are authenticated with actual data commencing the UCI machine learning datasets. Furthermore, the concert of the fuzzy expert structure is appraised by equating it to connected work that used the MFIS to detect the occurrence of type 2 diabetes. Objective: This survey paper presents a review of recent advances in the area of machine learning based classification models for diagnosis of diabetes. Methods: This paper presents an extensive work done in the field of machine learning based classification models for diagnosis of type 2 diabetes where modified fusion of machine learning methods are compared to the basic models i.e. Radial basis function, K-nearest neighbor, support vector machine, J48, logistic regression, classification and regression tress etc. based on training and testing. Results: Fig. 3 and Fig. 4 summarizes the result based on prediction accurateness for each classifier of training and testing. Conclusion: The fuzzy expert system is the best among its rival classifiers; SVM performs very poorly with a very low true positive rate, i.e. a very high number of positive cases misclassified as (Non-diabetic) negative. Based on the evaluation it is clear that the fuzzy expert system has the highest precision value. However, J48 is the least accurate classifier. It has the highest number of false positives relative to the other classifiers mentioned in the testing part. The results show that the fuzzy expert system has the uppermost cost for both precision and recall. Thus, it has the uppermost value for F-measure in the training and testing datasets. J48 is considered the second-best classifier for the training dataset, whereas Naïve Bayes comes in the second rank in the testing dataset.

Download Full-text

Evaluation of Different Machine Learning Algorithms for Scalable Classification of Tree Types and Tree Species Based on Sentinel-2 Data

Remote Sensing ◽

10.3390/rs10091419 ◽

2018 ◽

Vol 10 (9) ◽

pp. 1419 ◽

Cited By ~ 31

Author(s):

Mathias Wessel ◽

Melanie Brandmeier ◽

Dirk Tiede

Keyword(s):

Machine Learning ◽

Tree Species ◽

Confusion Matrix ◽

Machine Learning Algorithms ◽

Support Vector ◽

Inventory Data ◽

Oak Trees ◽

Object Based ◽

Sentinel 2

We use freely available Sentinel-2 data and forest inventory data to evaluate the potential of different machine-learning approaches to classify tree species in two forest regions in Bavaria, Germany. Atmospheric correction was applied to the level 1C data, resulting in true surface reflectance or bottom of atmosphere (BOA) output. We developed a semiautomatic workflow for the classification of deciduous (mainly spruce trees), beech and oak trees by evaluating different classification algorithms (object- and pixel-based) in an architecture optimized for distributed processing. A hierarchical approach was used to evaluate different band combinations and algorithms (Support Vector Machines (SVM) and Random Forest (RF)) for the separation of broad-leaved vs. coniferous trees. The Ebersberger forest was the main project region and the Freisinger forest was used in a transferability study. Accuracy assessment and training of the algorithms was based on inventory data, validation was conducted using an independent dataset. A confusion matrix, with User´s and Producer´s Accuracies, as well as Overall Accuracies, was created for all analyses. In total, we tested 16 different classification setups for coniferous vs. broad-leaved trees, achieving the best performance of 97% for an object-based multitemporal SVM approach using only band 8 from three scenes (May, August and September). For the separation of beech and oak trees we evaluated 54 different setups, the best result achieved an accuracy of 91% for an object-based, SVM, multitemporal approach using bands 8, 2 and 3 of the May scene for segmentation and all principal components of the August scene for classification. The transferability of the model was tested for the Freisinger forest and showed similar results. This project points out that Sentinel-2 had only marginally worse results than comparable commercial high-resolution satellite sensors and is well-suited for forest analysis on a tree-stand level.

Download Full-text

Improved Accuracy of Phenological Detection in Rice Breeding by Using Ensemble Models of Machine Learning Based on UAV-RGB Imagery

Remote Sensing ◽

10.3390/rs13142678 ◽

2021 ◽

Vol 13 (14) ◽

pp. 2678

Author(s):

Haixiao Ge ◽

Fei Ma ◽

Zhenwang Li ◽

Zhengzheng Tan ◽

Changwen Du

Keyword(s):

Machine Learning ◽

Time Series ◽

Vegetation Index ◽

Color Space ◽

Machine Learning Algorithms ◽

Majority Voting ◽

Support Vector ◽

Rice Breeding ◽

Phenological Stages ◽

Ensemble Models

Accurate and timely detection of phenology at plot scale in rice breeding trails is crucial for understanding the heterogeneity of varieties and guiding field management. Traditionally, remote sensing studies of phenology detection have heavily relied on the time-series vegetation index (VI) data. However, the methodology based on time-series VI data was often limited by the temporal resolution. In this study, three types of ensemble models including hard voting (majority voting), soft voting (weighted majority voting) and model stacking, were proposed to identify the principal phenological stages of rice based on unmanned aerial vehicle (UAV) RGB imagery. These ensemble models combined RGB-VIs, color space (e.g., RGB and HSV) and textures derived from UAV-RGB imagery, and five machine learning algorithms (random forest; k-nearest neighbors; Gaussian naïve Bayes; support vector machine and logistic regression) as base models to estimate phenological stages in rice breeding. The phenological estimation models were trained on the dataset of late-maturity cultivars and tested independently on the dataset of early-medium-maturity cultivars. The results indicated that all ensemble models outperform individual machine learning models in all datasets. The soft voting strategy provided the best performance for identifying phenology with the overall accuracy of 90% and 93%, and the mean F1-scores of 0.79 and 0.81, respectively, in calibration and validation datasets, which meant that the overall accuracy and mean F1-scores improved by 5% and 7%, respectively, in comparison with those of the best individual model (GNB), tested in this study. Therefore, the ensemble models demonstrated great potential in improving the accuracy of phenology detection in rice breeding.

Download Full-text